On the Foundations of the Design-Based Approach

2025-05-15

AI Summary

The Stable Unit Treatment Value Assumption (SUTVA) often fails in causal inference when interference—such as spillover effects—is present, undermining standard identification strategies. Method: We propose a paradigm shift from “assumption-first” to “model-driven, assumption-posterior” inference. Specifically, we develop a nonparametric generalized model that explicitly encodes interference structures; define novel identifiable causal targets via causal graph reasoning; and introduce the weak No-Unobserved-Residual-Variation Assumption (NURVA) to clarify identification conditions. Contribution/Results: This work provides the first systematic deconstruction of SUTVA’s logical role, proving both its irreplaceability under conventional frameworks and its practical limitations. Through assumption sensitivity analysis, we demonstrate the robustness and interpretability of our framework. Our approach establishes a more flexible, transparent, and design-oriented theoretical foundation for causal inference and survey sampling in the presence of interference.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Knowledge Representation and Reasoning: Nonmonotonic Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

The design-based paradigm may be adopted in causal queries and survey sampling when we assume Rubin's stable unit treatment value assumption (SUTVA) or impose similar frameworks. While often taken for granted, such assumptions entail strong claims about the data generating process. We develop an alternative design-based approach: we first invoke a generalized, non-parametric model that allows for unrestricted forms of interference, such as spillover. We define a new set of inferential targets and discuss their interpretation under SUTVA and a weaker assumption that we call the No Unmodeled Revealable Variation Assumption (NURVA). We then reconstruct the standard paradigm, reconsidering SUTVA at the end rather than assuming it at the beginning. Despite its similarity to SUTVA, we demonstrate the practical insufficiency of NURVA in identifying substantively interesting quantities. In so doing, we provide clarity on the nature and importance of SUTVA for applied research.

Problem

• Develops alternative design-based approach allowing interference
• Defines new inferential targets under weaker assumptions
• Reassesses SUTVA's necessity for causal identification

Innovation

• Generalized non-parametric model for interference
• New inferential targets under NURVA and SUTVA
• Reconstructed paradigm reconsidering SUTVA last